Free Online Tools for AI & LLM Developers
Utilities for building on top of large language models
Working with large language models introduces a new set of constraints most developer tooling was not designed for: token budgets instead of character limits, per-token pricing instead of flat rates, and different tokenizers for different model families. This category holds practical utilities that fit those constraints — starting with a token counter that estimates the cost and length of a prompt across GPT, Claude, and Gemini before you spend real money on an API call.
All Tools for AI & LLM Developers
Text Chunker
Split long text into overlapping chunks for embedding and RAG pipelines. Preview recursive, paragraph, sentence, or fixed strategies with live token counts. Runs 100% in your browser.
Cosine Similarity
Compute cosine similarity, dot product, and Euclidean distance between two vectors online. Perfect for debugging LLM embeddings, semantic search, and RAG pipelines. 100% local — vectors never leave your browser.
AI Cost Calculator
Estimate monthly LLM API cost across GPT-4o, Claude 3.5, Gemini, DeepSeek and 100+ models. Compare providers side-by-side with prompt-caching and batch discounts. Free, no signup — prices refreshed daily from the public LiteLLM catalog.
Token Counter
Count tokens in your prompt for GPT-4, GPT-3.5, Claude, and Gemini and predict API cost before you spend. Free, no signup — all counting runs locally, your prompt stays in your browser.
LLM JSON Extractor
Extract every JSON object or array buried inside an LLM reply — even when it's wrapped in markdown fences, mixed with explanation text, or has trailing commas and single quotes. Auto-repairs each block. 100% local.
Context Window Checker
Check whether your prompt fits a model's context window before you send it. Estimates prompt tokens, reserves room for the response, and shows remaining headroom across GPT-4o, o1, Claude, Gemini, DeepSeek and more. 100% local.
Prompt Token Breakdown
Break a prompt into segments and see how many tokens — and how much cost — each part uses. Find the heaviest section (system, few-shot examples, or user input) so you know exactly what to trim. 100% local.
Schema → Tool Definition
Turn a sample JSON payload into function-calling / tool definitions for OpenAI, Anthropic, and Gemini — side by side. Strict-mode toggle adds required + additionalProperties: false. 100% local, paste straight into your tools array.
Chat Messages Validator
Validate a Chat Completions messages array before you send it — checks roles (system/user/assistant/tool), required content, and common mistakes that cause a 400. 100% local.
Prompt Template Tester
Write a prompt with {{variable}} placeholders, fill in values, and preview the final prompt. Detects every variable and flags any you left unfilled. 100% local.
Prompt Diff
Compare two versions of a prompt line by line and see the token delta between them — so you know exactly what changed and whether an edit made the prompt cheaper or more expensive. 100% local.
Embedding Cost Calculator
Estimate the cost of embedding a corpus — pick a model, enter the number of documents and average tokens each, and get the total token count and dollar cost. 100% local.
Vector Storage Calculator
Estimate how much memory or disk your embeddings need — enter vector count, dimensions, and precision (float32/float16/int8/binary) to see raw and indexed size. 100% local.
Prompt Cache Calculator
See how much prompt caching saves you. Enter your cached prefix size, per-request tokens, volume, and hit rate to compare cost with and without caching across models that support it. 100% local.
Batch API Cost Calculator
Compare real-time vs Batch API cost for a bulk job. Enter request count and per-request tokens to see how much the ~50% batch discount saves across models that support it. 100% local.
Prompt Injection Detector
Scan untrusted user input for common prompt-injection and jailbreak patterns — instruction overrides, jailbreak personas, system-prompt exfiltration — with a risk score. Heuristic, 100% local.
When to use these tools
Use these tools when preparing a prompt for a large batch job, comparing how the same content is priced across model families, or trimming a prompt to fit under a specific context window.
Frequently Asked Questions
How accurate is the token count?
The estimator matches `tiktoken` (OpenAI's official tokenizer) within a few percent for typical English and code inputs. For billing-critical decisions, run the official tokenizer for your target model.
Do different LLM providers count tokens the same way?
No. GPT uses cl100k_base BPE, Claude uses a similar but distinct BPE vocabulary, and Gemini uses SentencePiece. The same text can differ by 10–15% across providers.